US20060107001A1 - Arbitration scheme for memory command selectors - Google Patents
Arbitration scheme for memory command selectors Download PDFInfo
- Publication number
- US20060107001A1 US20060107001A1 US10/988,311 US98831104A US2006107001A1 US 20060107001 A1 US20060107001 A1 US 20060107001A1 US 98831104 A US98831104 A US 98831104A US 2006107001 A1 US2006107001 A1 US 2006107001A1
- Authority
- US
- United States
- Prior art keywords
- commands
- read
- write
- executed
- command
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/16—Handling requests for interconnection or transfer for access to memory bus
- G06F13/1605—Handling requests for interconnection or transfer for access to memory bus based on arbitration
- G06F13/161—Handling requests for interconnection or transfer for access to memory bus based on arbitration with latency improvement
- G06F13/1626—Handling requests for interconnection or transfer for access to memory bus based on arbitration with latency improvement by reordering requests
Definitions
- the present invention relates generally to a memory command arbiter, and more particularly, to a memory control arbiter that can handle different memory devices at high bandwidths with low read latency.
- An arbitration scheme for memory commands can be described as a hierarchy that determines which memory command has immediate priority to use a specific data channel.
- memory systems are managed by a group of commands that accomplish the necessary operations of the memory system. These operations consist of read, write, and periodic commands.
- Read commands receive data from memory cells in response to a request for that data.
- Write commands transmit data to memory cells to be stored.
- Periodic commands consist of a memory refresh or a memory scrub, which must be executed within a certain time window.
- a memory refresh command maintains the current value of the memory cells. If a cell is not refreshed in a specific amount of time, the data becomes unstable.
- a memory scrub command reads the data from the memory cells to check for data errors. If there is a single bit error, the error is fixed and the data is stored back into memory.
- Arbitration schemes determine the order in which these commands are accomplished by the memory system. In every memory system there is a limited amount of data bandwidth that can be used to accomplish the necessary memory commands.
- the read, write and periodic commands request to gain ownership of a data channel, and the arbiter grants ownership of the specific channel to the chosen command.
- the order in which the commands are chosen for each memory subsystem is unique. Some subsystems have a larger delay when switching between different types of commands. In a system where there is a large delay, the arbiter wants to select the same type of command for as long as it can before transferring to a different command. In a system where there is no delay, the arbiter has more freedom to choose the command based on how full its queues are or to choose multiple read commands to reduce read latency.
- the present invention provides an arbitration structure, a method, and a computer program for an arbitration scheme that can handle a plurality of memory commands in an operating system.
- a memory system there are three types of operations: periodic, read, and write. These operations are accomplished by issuing commands that correspond to the particular operations.
- An arbitration scheme determines the order of priority in which these commands are executed.
- This arbitration scheme is flexible because it contains a read/write priority module.
- the read/write priority module can be programmed to execute any order of priority combination of read and write commands. This enables an arbitration scheme for any memory system to be easily programmed so that the memory commands are executed efficiently. By maximizing efficiency, this invention allows memory systems to operate at high bandwidths with a low read latency.
- FIG. 1 is a flow chart illustrating a modified multiple stage arbitration scheme for use in a memory controller
- FIG. 2 is a block diagram illustrating an apparatus designed for a multiple stage arbitration scheme for use in a memory controller.
- reference numeral 100 is a flow chart illustrating a modified multiple stage arbitration scheme for use in a memory controller.
- the periodic commands consist of a memory refresh or a memory scrub.
- the arbitration scheme 100 contains two stages. The first stage consists of preparing a read or write operation to be executed from the read 102 or write queues 104 . The second stage involves the selection of the highest-priority command and the execution of that command.
- Read queue 102 signifies a stack of read operations that need to be executed.
- Write queue 104 signifies a stack of write operations that need to be executed.
- the commands for the read 102 and the write queues 104 are arbitrated individually in the first stage.
- the oldest command to an available memory bank step 106 depicts that the oldest read operation in the read queue 102 is selected by the arbiter first.
- the oldest command to available memory bank step 108 depicts that the oldest write operation in the write queue 104 is selected by the arbiter first. These steps 106 and 108 are shown because the arbiter must first select the commands that have been waiting to be executed the longest.
- the oldest commands are paired with an available bank 110 from the bank sequencer pool.
- the available banks 110 step refers to the bank sequencers that are idle and can be used to execute an operation.
- the next read command 112 signifies that the oldest read command 106 is paired with an available bank 110 and the read operation is ready to be executed.
- the next write command 114 signifies that the oldest write command 108 is paired with an available bank 110 and the write operation is ready to be executed.
- the command selection stage 118 is the core of the arbitration scheme. This is where the specific commands (read, write or periodic) are selected to be executed 122 .
- the periodic commands 116 , the next read command 112 , the next write command 114 , and the read/write priority 120 are all provided to the command selection 118 .
- Periodic commands 116 must be executed within a certain time window, so they 116 are chosen ahead of read 112 and write commands 114 at the command selection stage 118 .
- the read/write priority 120 determines the priority order of the read 112 and write commands 114 .
- the read/write priority 120 can be programmed to execute any combination of read 112 and write commands 114 , which means that it can be configured to any memory system's specifications.
- the memory system contains eight banks, and four banks are the most that can be in use at any one time.
- the read/write priority 120 is core concept of this modified arbitration scheme 100 .
- the read/write priority 120 is configurable based upon the memory device specifications. If the memory device has a large turnaround delay from reads to writes, or from writes to reads, the read/write priority 120 can be set up to influence the command selection 118 to choose commands of the same type. For example, the read/write priority 120 can be programmed to do 16 read commands 112 in a row. This causes the write commands to pile up at the write queue 104 , so that you can send a large group of write commands 114 in a row. In this example there is only one read to write turnaround and one write to read turnaround for every 16 read commands, which indicates that the memory commands are executed more efficiently.
- This feature of the arbitration scheme 100 allows for maximum bandwidth because there is a drastic decrease in down time that is caused by turnaround delays. This feature also minimizes read latency because reads can be executed more quickly without turnaround delays.
- This arbitration scheme 100 provides a flexible, fast, and efficient solution to memory command selection.
- reference numeral 200 is a block diagram illustrating an apparatus designed for a multiple stage arbitration scheme for use in a memory controller.
- a processing unit 202 is the module that accomplishes the logical functions of the memory system.
- the communication channel 212 connects the processing unit 202 to queues 204 .
- the queues 204 is a storage module that assembles a line of operations (read and write operations) to be carried out. Accordingly, the processing unit 202 determines what operations need to be accomplished and transmits these operations on the communication channel 212 to be stored by the queues 204 .
- Communication channel 214 connects the processing unit 202 to an interface 206 .
- the interface module 206 selects the commands (read, write, or periodic) that are to be executed.
- the processing unit 202 controls the periodic commands 116 ( FIG. 1 ), so if a periodic command must be accomplished then it is transmitted to the interface 206 on communication channel 214 .
- the queues 204 are connected to the interface 206 by communication channel 216 .
- the queues 204 transmit the next commands (read or write) to be executed by the interface 206 over communication channel 216 .
- the interface module 206 is connected to a bus 210 by connection channel 218 .
- the resources (banks) 208 are connected to the same bus 210 by connection channel 220 .
- the interface module 206 provides the next command to be executed (read, write, or periodic) and the resources (banks) 208 provide an available bank to accomplish the command.
- the bus 210 is used to execute the command and transmit the resulting data.
- FIG. 2 illustrates only one embodiment of an apparatus that can be configured to accomplish this multiple stage arbitration scheme.
Abstract
Description
- The present invention relates generally to a memory command arbiter, and more particularly, to a memory control arbiter that can handle different memory devices at high bandwidths with low read latency.
- An arbitration scheme for memory commands can be described as a hierarchy that determines which memory command has immediate priority to use a specific data channel. Typically, memory systems are managed by a group of commands that accomplish the necessary operations of the memory system. These operations consist of read, write, and periodic commands. Read commands receive data from memory cells in response to a request for that data. Write commands transmit data to memory cells to be stored. Periodic commands consist of a memory refresh or a memory scrub, which must be executed within a certain time window. A memory refresh command maintains the current value of the memory cells. If a cell is not refreshed in a specific amount of time, the data becomes unstable. A memory scrub command reads the data from the memory cells to check for data errors. If there is a single bit error, the error is fixed and the data is stored back into memory.
- Arbitration schemes determine the order in which these commands are accomplished by the memory system. In every memory system there is a limited amount of data bandwidth that can be used to accomplish the necessary memory commands. The read, write and periodic commands request to gain ownership of a data channel, and the arbiter grants ownership of the specific channel to the chosen command. The order in which the commands are chosen for each memory subsystem is unique. Some subsystems have a larger delay when switching between different types of commands. In a system where there is a large delay, the arbiter wants to select the same type of command for as long as it can before transferring to a different command. In a system where there is no delay, the arbiter has more freedom to choose the command based on how full its queues are or to choose multiple read commands to reduce read latency.
- The problem is that conventional arbitration schemes are not flexible. Conventional arbitration schemes are not robust enough to handle a wide range of memory devices and memory systems. The conventional arbitration schemes must be hard coded to match the memory system they are designed with. Different memory systems need to be configured with unique arbitration schemes, which means that implementation is not easy or efficient. It is clear that a modified arbitration scheme is needed to provide more flexibility with implementation and to make memory systems more efficient.
- The present invention provides an arbitration structure, a method, and a computer program for an arbitration scheme that can handle a plurality of memory commands in an operating system. Typically, in a memory system there are three types of operations: periodic, read, and write. These operations are accomplished by issuing commands that correspond to the particular operations. An arbitration scheme determines the order of priority in which these commands are executed. This arbitration scheme is flexible because it contains a read/write priority module. The read/write priority module can be programmed to execute any order of priority combination of read and write commands. This enables an arbitration scheme for any memory system to be easily programmed so that the memory commands are executed efficiently. By maximizing efficiency, this invention allows memory systems to operate at high bandwidths with a low read latency.
- For a more complete understanding of the present invention and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:
-
FIG. 1 is a flow chart illustrating a modified multiple stage arbitration scheme for use in a memory controller; -
FIG. 2 is a block diagram illustrating an apparatus designed for a multiple stage arbitration scheme for use in a memory controller. - In the following discussion, numerous specific details are set forth to provide a thorough understanding of the present invention. However, those skilled in the art will appreciate that the present invention may be practiced without such specific details. In other instances, well-known elements have been illustrated in block diagram or flow chart form in order not to obscure the present invention in unnecessary detail. Additionally, for the most part, details concerning network communications, electromagnetic signaling techniques, and the like, have been omitted inasmuch as such details are not considered necessary to obtain a complete understanding of the present invention, and are considered to be within the understanding of persons of ordinary skill in the relevant art.
- When designing an arbitration scheme for memory command selection, there are a couple of features to be concerned with. Maximum bandwidth and minimum read latency must be realized in these designs. To achieve maximum bandwidth, the memory system should be able to handle a high amount of data traffic without any dead time. To achieve minimum read latency, the memory system should be able to accomplish read and write operations in the shortest period of time possible. Read latency can be negatively affected by read operation cycle time and read to write or write to read turnaround delays.
- Referring to
FIG. 1 of the drawings,reference numeral 100 is a flow chart illustrating a modified multiple stage arbitration scheme for use in a memory controller. There are three types of commands that this arbitration scheme controls: read, write and periodic commands. The periodic commands consist of a memory refresh or a memory scrub. Thearbitration scheme 100 contains two stages. The first stage consists of preparing a read or write operation to be executed from theread 102 or writequeues 104. The second stage involves the selection of the highest-priority command and the execution of that command. Readqueue 102 signifies a stack of read operations that need to be executed. Writequeue 104 signifies a stack of write operations that need to be executed. The commands for theread 102 and thewrite queues 104 are arbitrated individually in the first stage. The oldest command to an availablememory bank step 106 depicts that the oldest read operation in theread queue 102 is selected by the arbiter first. The oldest command to availablememory bank step 108 depicts that the oldest write operation in thewrite queue 104 is selected by the arbiter first. Thesesteps steps available bank 110 from the bank sequencer pool. Theavailable banks 110 step refers to the bank sequencers that are idle and can be used to execute an operation. - The
next read command 112 signifies that theoldest read command 106 is paired with anavailable bank 110 and the read operation is ready to be executed. Thenext write command 114 signifies that theoldest write command 108 is paired with anavailable bank 110 and the write operation is ready to be executed. Thecommand selection stage 118 is the core of the arbitration scheme. This is where the specific commands (read, write or periodic) are selected to be executed 122. Theperiodic commands 116, thenext read command 112, thenext write command 114, and the read/write priority 120 are all provided to thecommand selection 118. - Periodic commands 116 must be executed within a certain time window, so they 116 are chosen ahead of
read 112 and writecommands 114 at thecommand selection stage 118. The read/write priority 120 determines the priority order of theread 112 and write commands 114. The read/write priority 120 can be programmed to execute any combination ofread 112 and writecommands 114, which means that it can be configured to any memory system's specifications. When the highest-priority command is selected 118, that command is then executed 122. After the command is executed the bank that executed the command is unavailable for a configurable amount of time. After this period of time the bank becomes available 110 and it may be used for another operation. During that delay time, all the other banks may be used to execute commands. Accordingly, the newavailable bank 110 is then ready to execute theoldest read command 106 or theoldest write command 108. In one embodiment of this arbitration scheme, the memory system contains eight banks, and four banks are the most that can be in use at any one time. - This
arbitration scheme design 100 provides many advantages over previous arbitration schemes. The read/write priority 120 is core concept of this modifiedarbitration scheme 100. The read/write priority 120 is configurable based upon the memory device specifications. If the memory device has a large turnaround delay from reads to writes, or from writes to reads, the read/write priority 120 can be set up to influence thecommand selection 118 to choose commands of the same type. For example, the read/write priority 120 can be programmed to do 16 read commands 112 in a row. This causes the write commands to pile up at thewrite queue 104, so that you can send a large group of write commands 114 in a row. In this example there is only one read to write turnaround and one write to read turnaround for every 16 read commands, which indicates that the memory commands are executed more efficiently. This feature of thearbitration scheme 100 allows for maximum bandwidth because there is a drastic decrease in down time that is caused by turnaround delays. This feature also minimizes read latency because reads can be executed more quickly without turnaround delays. - Another advantage of this
arbitration scheme 100 is its flexibility. The programmability of the read/write priority 120 ensures that this arbitration scheme can be implemented to achieve maximum efficiency from any memory system. The read/write priority 120 is programmed by setting a few registers to the desired specifications. Conventional arbitration schemes are not easily programmed, and therefore, a new chip is required to be entirely configured for each specific memory system. Overall, thisarbitration scheme 100 provides a flexible, fast, and efficient solution to memory command selection. - Referring to
FIG. 2 of the drawings,reference numeral 200 is a block diagram illustrating an apparatus designed for a multiple stage arbitration scheme for use in a memory controller. Aprocessing unit 202 is the module that accomplishes the logical functions of the memory system. Thecommunication channel 212 connects theprocessing unit 202 toqueues 204. Thequeues 204 is a storage module that assembles a line of operations (read and write operations) to be carried out. Accordingly, theprocessing unit 202 determines what operations need to be accomplished and transmits these operations on thecommunication channel 212 to be stored by thequeues 204.Communication channel 214 connects theprocessing unit 202 to aninterface 206. Theinterface module 206 selects the commands (read, write, or periodic) that are to be executed. Theprocessing unit 202 controls the periodic commands 116 (FIG. 1 ), so if a periodic command must be accomplished then it is transmitted to theinterface 206 oncommunication channel 214. Thequeues 204 are connected to theinterface 206 bycommunication channel 216. Thequeues 204 transmit the next commands (read or write) to be executed by theinterface 206 overcommunication channel 216. - The
interface module 206 is connected to abus 210 byconnection channel 218. The resources (banks) 208 are connected to thesame bus 210 byconnection channel 220. Theinterface module 206 provides the next command to be executed (read, write, or periodic) and the resources (banks) 208 provide an available bank to accomplish the command. Thebus 210 is used to execute the command and transmit the resulting data.FIG. 2 illustrates only one embodiment of an apparatus that can be configured to accomplish this multiple stage arbitration scheme. - It is understood that the present invention can take many forms and embodiments. Accordingly, several variations of the present design may be made without departing from the scope of the invention. The capabilities outlined herein allow for the possibility of a variety of programming models. This disclosure should not be read as preferring any particular programming model, but is instead directed to the underlying concepts on which these programming models can be built.
- Having thus described the present invention by reference to certain of its preferred embodiments, it is noted that the embodiments disclosed are illustrative rather than limiting in nature and that a wide range of variations, modifications, changes, and substitutions are contemplated in the foregoing disclosure and, in some instances, some features of the present invention may be employed without a corresponding use of the other features. Many such variations and modifications may be considered desirable by those skilled in the art based upon a review of the foregoing description of preferred embodiments. Accordingly, it is appropriate that the appended claims be construed broadly and in a manner consistent with the scope of the invention.
Claims (19)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/988,311 US7272692B2 (en) | 2004-11-12 | 2004-11-12 | Arbitration scheme for memory command selectors |
CNB2005101194433A CN100382060C (en) | 2004-11-12 | 2005-11-11 | An arbitration structure and a method for handling a plurality of memory commands |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/988,311 US7272692B2 (en) | 2004-11-12 | 2004-11-12 | Arbitration scheme for memory command selectors |
Publications (2)
Publication Number | Publication Date |
---|---|
US20060107001A1 true US20060107001A1 (en) | 2006-05-18 |
US7272692B2 US7272692B2 (en) | 2007-09-18 |
Family
ID=36387795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/988,311 Active 2025-10-20 US7272692B2 (en) | 2004-11-12 | 2004-11-12 | Arbitration scheme for memory command selectors |
Country Status (2)
Country | Link |
---|---|
US (1) | US7272692B2 (en) |
CN (1) | CN100382060C (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017054483A (en) * | 2015-09-08 | 2017-03-16 | ソニー株式会社 | Memory controller, memory system, and control method of memory controller |
US20180233214A1 (en) * | 2016-02-29 | 2018-08-16 | SK Hynix Inc. | Test apparatus and semiconductor chip |
US11221798B2 (en) * | 2018-08-17 | 2022-01-11 | Apple Inc. | Write/read turn techniques based on latency tolerance |
US11599424B2 (en) * | 2019-08-15 | 2023-03-07 | Cisco Technology, Inc. | Dynamic hardware resource shadowing and memory error protection |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070168754A1 (en) * | 2005-12-19 | 2007-07-19 | Xiv Ltd. | Method and apparatus for ensuring writing integrity in mass storage systems |
US7617368B2 (en) * | 2006-06-14 | 2009-11-10 | Nvidia Corporation | Memory interface with independent arbitration of precharge, activate, and read/write |
CN101043445B (en) * | 2007-03-06 | 2011-02-23 | 哈尔滨工程大学 | IO dispatch method in network storage system |
US20090196143A1 (en) * | 2008-02-06 | 2009-08-06 | Nils Haustein | Method and System for Command-Ordering for a Disk-to-Disk-to-Holographic Data Storage System |
JPWO2013014841A1 (en) * | 2011-07-22 | 2015-02-23 | パナソニック株式会社 | Data processing apparatus and data processing method |
CN105610662B (en) * | 2015-12-29 | 2019-01-22 | 北京理工大学 | The feedback type comprehensive dynamic dispatching control based on network device of electric car |
US10732897B2 (en) * | 2018-07-03 | 2020-08-04 | Western Digital Technologies, Inc. | Quality of service based arbitrations optimized for enterprise solid state drives |
US10866764B2 (en) * | 2018-07-23 | 2020-12-15 | SK Hynix Inc. | Memory system with parity cache scheme and method of operating such memory system |
US11455124B2 (en) | 2020-10-09 | 2022-09-27 | Western Digital Technologies, Inc. | Command prioritization to reduce latencies of zone commands |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6092158A (en) * | 1997-06-13 | 2000-07-18 | Intel Corporation | Method and apparatus for arbitrating between command streams |
US6101614A (en) * | 1994-05-24 | 2000-08-08 | Intel Corporation | Method and apparatus for automatically scrubbing ECC errors in memory via hardware |
US6112265A (en) * | 1997-04-07 | 2000-08-29 | Intel Corportion | System for issuing a command to a memory having a reorder module for priority commands and an arbiter tracking address of recently issued command |
US6182177B1 (en) * | 1997-06-13 | 2001-01-30 | Intel Corporation | Method and apparatus for maintaining one or more queues of elements such as commands using one or more token queues |
US20030229755A1 (en) * | 2002-06-06 | 2003-12-11 | International Business Machines Corporation | Dynamic response shaping for command aging |
US6671761B2 (en) * | 2000-08-11 | 2003-12-30 | Samsung Electronics Co., Ltd. | Bus system |
US20040004883A1 (en) * | 2002-07-04 | 2004-01-08 | Fujitsu Limited | Semiconductor memory |
US20050105372A1 (en) * | 2003-10-30 | 2005-05-19 | Fujitsu Limited | Semiconductor memory |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4493036A (en) * | 1982-12-14 | 1985-01-08 | Honeywell Information Systems Inc. | Priority resolver having dynamically adjustable priority levels |
US5640563A (en) * | 1992-01-31 | 1997-06-17 | International Business Machines Corporation | Multi-media computer operating system and method |
US5978852A (en) * | 1998-01-06 | 1999-11-02 | 3Com Corporation | LAN switch interface for providing arbitration between different simultaneous memory access requests |
CN1279450C (en) * | 2002-11-13 | 2006-10-11 | 矽统科技股份有限公司 | Memory reading or writing arbitration method |
-
2004
- 2004-11-12 US US10/988,311 patent/US7272692B2/en active Active
-
2005
- 2005-11-11 CN CNB2005101194433A patent/CN100382060C/en not_active Expired - Fee Related
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6101614A (en) * | 1994-05-24 | 2000-08-08 | Intel Corporation | Method and apparatus for automatically scrubbing ECC errors in memory via hardware |
US6112265A (en) * | 1997-04-07 | 2000-08-29 | Intel Corportion | System for issuing a command to a memory having a reorder module for priority commands and an arbiter tracking address of recently issued command |
US6092158A (en) * | 1997-06-13 | 2000-07-18 | Intel Corporation | Method and apparatus for arbitrating between command streams |
US6182177B1 (en) * | 1997-06-13 | 2001-01-30 | Intel Corporation | Method and apparatus for maintaining one or more queues of elements such as commands using one or more token queues |
US6671761B2 (en) * | 2000-08-11 | 2003-12-30 | Samsung Electronics Co., Ltd. | Bus system |
US20030229755A1 (en) * | 2002-06-06 | 2003-12-11 | International Business Machines Corporation | Dynamic response shaping for command aging |
US20040004883A1 (en) * | 2002-07-04 | 2004-01-08 | Fujitsu Limited | Semiconductor memory |
US20050105372A1 (en) * | 2003-10-30 | 2005-05-19 | Fujitsu Limited | Semiconductor memory |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017054483A (en) * | 2015-09-08 | 2017-03-16 | ソニー株式会社 | Memory controller, memory system, and control method of memory controller |
US20180232178A1 (en) * | 2015-09-08 | 2018-08-16 | Sony Corporation | Memory controller, memory system, and method of controlling memory controller |
US20180233214A1 (en) * | 2016-02-29 | 2018-08-16 | SK Hynix Inc. | Test apparatus and semiconductor chip |
US10566073B2 (en) * | 2016-02-29 | 2020-02-18 | SK Hynix Inc. | Test apparatus and semiconductor chip |
US11221798B2 (en) * | 2018-08-17 | 2022-01-11 | Apple Inc. | Write/read turn techniques based on latency tolerance |
US11599424B2 (en) * | 2019-08-15 | 2023-03-07 | Cisco Technology, Inc. | Dynamic hardware resource shadowing and memory error protection |
US11822437B2 (en) | 2019-08-15 | 2023-11-21 | Cisco Technology, Inc. | Dynamic hardware resource shadowing and memory error protection |
Also Published As
Publication number | Publication date |
---|---|
US7272692B2 (en) | 2007-09-18 |
CN1773475A (en) | 2006-05-17 |
CN100382060C (en) | 2008-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11199996B2 (en) | Method of scheduling requests to banks in a flash controller | |
CN100382060C (en) | An arbitration structure and a method for handling a plurality of memory commands | |
US10761772B2 (en) | Memory system including a plurality of chips and a selectively-connecting bus | |
KR101371815B1 (en) | Memory controllers, memory systems, solid state drivers and methods for processing a number of commands | |
US7246188B2 (en) | Flow control method to improve bus utilization in a system-on-a-chip integrated circuit | |
TWI421680B (en) | Parallel flash memory controller | |
JP4024875B2 (en) | Method and apparatus for arbitrating access to shared memory for network ports operating at different data rates | |
US10552047B2 (en) | Memory system | |
CN103336669B (en) | A kind of I/O dispatching method based on solid-state disk internal concurrency and scheduler | |
EP3368989B1 (en) | Intelligent coded memory architecture with enhanced access scheduler | |
US20170344506A1 (en) | Qos-aware io management for pcie storage system with reconfigurable multi-ports | |
US20120102262A1 (en) | Memory control device, storage device, and memory control method | |
US10078471B2 (en) | Memory device that sorts access commands to a nonvolatile semiconductor memory unit thereof | |
US11029746B2 (en) | Dynamic power management network for memory devices | |
US7725621B2 (en) | Semiconductor device and data transfer method | |
US20140325114A1 (en) | Multi-channel direct memory access controller and control method thereof | |
US9971546B2 (en) | Methods for scheduling read and write commands and apparatuses using the same | |
TW202230112A (en) | Plane-based queue configuration for aipr-enabled drives | |
US7346722B2 (en) | Apparatus for use in a computer systems | |
US20200409846A1 (en) | Dual controller cache optimization in a deterministic data storage system | |
JPH08235092A (en) | Data transfer controller | |
CN112506431B (en) | I/O instruction scheduling method and device based on disk device attributes | |
KR102242957B1 (en) | High speed NAND memory system and high speed NAND memory package device | |
JP2505021B2 (en) | Main memory controller | |
KR100790168B1 (en) | Booting method and apparatus for using nand flash memory in a processing system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BARNUM, MELISSA ANN;HASELHORST, KENT HAROLD;LAMBRECHT, LONNY;REEL/FRAME:015504/0091 Effective date: 20041109 Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BARNUM, MELISSA ANN;HASELHORST, KENT HAROLD;LAMBRECHT, LONNY;REEL/FRAME:015504/0037 Effective date: 20041109 Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BARNUM, MELISSA ANN;HASELHORST, KENT HAROLD;LAMBRECHT, LONNY;REEL/FRAME:015504/0064 Effective date: 20041109 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
REMI | Maintenance fee reminder mailed | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
SULP | Surcharge for late payment | ||
AS | Assignment |
Owner name: GOOGLE INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:026894/0001 Effective date: 20110817 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
AS | Assignment |
Owner name: GOOGLE LLC, CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:GOOGLE INC.;REEL/FRAME:044127/0735 Effective date: 20170929 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |